YOYO-AI/Qwen3-30B-A3B-YOYO-V2

Full fine-tune vs Qwen/Qwen3-30B-A3B-Base. Fine-tune: 100% of the weights changed, across 48 of 48 layers.

Tensors changed: Norms 193/193, MLP 2613/2613, Attention 192/192

3 derivatives checked

• mradermacher/Qwen3-30B-A3B-YOYO-V2-i1-GGUF: Quantization
• DavidAU/Qwen3-30B-A3B-YOYO-V2-Claude-4.6-Opus-High-INSTRUCT: LoRA-style
• mradermacher/Qwen3-30B-A3B-YOYO-V2-GGUF: Quantization

On the Hub · Downloads on Model Pulse